Estimating plant nitrogen concentration (PNC) has been conducted using vegetation indices (VIs) from UAV-based imagery, but color features have been rarely considered as additional variables. In this study, the VIs and color moments (color feature) were calculated from UAV-based RGB images, then partial least square regression (PLSR) and random forest regression (RF) models were established to estimate PNC through fusing VIs and color moments. The results demonstrated that the fusion of VIs and color moments as inputs yielded higher accuracies of PNC estimation compared to VIs or color moments as input; the RF models based on the combination of VIs and color moments (R2 ranging from 0.69 to 0.91 and NRMSE ranging from 0.07 to 0.13) showed similar performances to the PLSR models (R2 ranging from 0.68 to 0.87 and NRMSE ranging from 0.10 to 0.29); Among the top five important variables in the RF models, there was at least one variable which belonged to the color moments in different datasets, indicating the significant contribution of color moments in improving PNC estimation accuracy. This revealed the great potential of combination of RGB-VIs and color moments for the estimation of rice PNC.
The accurate estimation of grain yield in rice breeding is crucial for breeders to screen and select qualified cultivars. In this study, a low-cost unmanned aerial vehicle (UAV) platform mounted with an RGB camera was carried out to capture high-spatial resolution images of rice canopy in rice breeding. The random forest (RF) regression techniques were used to establish yield models by using (1) only color vegetation indices (VIs), (2) only phenological data, and (3) fusion of VIs and phenological data as inputs, respectively. Then, the performances of RF models were compared with the manual observation and CERES-Rice model. The results indicated that the RF model using VIs only performed poorly for estimating yield; the optimized RF model that combined the use of phenological data and color VIs performed much better, which demonstrated that the phenological data significantly improved the model performance. Furthermore, the yield estimation accuracy of 21 rice cultivars that were continuously planted over three years in the optimal RF model had no significant difference (p > 0.05) with that of the CERES-Rice model. These findings demonstrate that the RF model, by combining phenological data and color Vis, is a potential and cost-effective way to estimate yield in rice breeding.
Accurate and timely detection of phenology at plot scale in rice breeding trails is crucial for understanding the heterogeneity of varieties and guiding field management. Traditionally, remote sensing studies of phenology detection have heavily relied on the time-series vegetation index (VI) data. However, the methodology based on time-series VI data was often limited by the temporal resolution. In this study, three types of ensemble models including hard voting (majority voting), soft voting (weighted majority voting) and model stacking, were proposed to identify the principal phenological stages of rice based on unmanned aerial vehicle (UAV) RGB imagery. These ensemble models combined RGB-VIs, color space (e.g., RGB and HSV) and textures derived from UAV-RGB imagery, and five machine learning algorithms (random forest; k-nearest neighbors; Gaussian naïve Bayes; support vector machine and logistic regression) as base models to estimate phenological stages in rice breeding. The phenological estimation models were trained on the dataset of late-maturity cultivars and tested independently on the dataset of early-medium-maturity cultivars. The results indicated that all ensemble models outperform individual machine learning models in all datasets. The soft voting strategy provided the best performance for identifying phenology with the overall accuracy of 90% and 93%, and the mean F1-scores of 0.79 and 0.81, respectively, in calibration and validation datasets, which meant that the overall accuracy and mean F1-scores improved by 5% and 7%, respectively, in comparison with those of the best individual model (GNB), tested in this study. Therefore, the ensemble models demonstrated great potential in improving the accuracy of phenology detection in rice breeding.
Global sensitivity analysis (SA) has become an efficient way to identify the most influential parameters on model results. However, the effects of cultivar variation and specific-stage variations of climate conditions on model outputs still remain unclear. In this study, 30 indica hybrid rice cultivars were simulated in the CERES-Rice model; then the Sobol’ method was used to perform a global SA on 16 investigated parameters for three model outputs (anthesis day, maturity day, and yield). In addition, we also compared the differences in the sensitivity results under four specific-stage variations (vegetative phase, panicle-formation phase, ripening phase, and the whole growth season) of climate conditions. The results indicated that (1) parameter Tavg, G4, and P2O are the most influential parameters for all model outputs across cultivars during the whole growth season; (2) under the vegetative-phase variation of climate parameters; the variability of model outputs is mainly controlled by parameter P2O and Tavg; (3) under the panicle-formation-phase or ripening-phase variation of climate parameters, parameter P2O was the dominant variable for all model outputs; (4) parameter PORM had a considerable effect (the total sensitivity index, STi; STi>0.05) on yield regardless of the various specific-stage variations of the climate parameters. Findings obtained from this study will contribute to understanding the comprehensive effects of crop parameters on model outputs under different cultivars and specific-stage variations of climate conditions.
Short episodes of low-temperature stress during reproductive stages can cause significant crop yield losses, but our understanding of the dynamics of extreme cold events and their impact on rice growth and yield in the past and present climate remains limited. In this study, by analyzing historical climate, phenology and yield component data, the spatial and temporal variability of cold stress during the rice heading and flowering stages and its impact on rice growth and yield in China was characterized. The results showed that cold stress was unevenly distributed throughout the study region, with the most severe events observed in the Yunnan Plateau with altitudes higher than 1800 m. With the increasing temperature, a significant decreasing trend in cold stress was observed across most of the three ecoregions after the 1970s. However, the phenological-shift effects with the prolonged growing period during the heading and flowering stages have slowed down the cold stress decreasing trend and led to an underestimation of the magnitude of cold stress events. Meanwhile, cold stress during heading and flowering will still be a potential threat to rice production. The cold stress-induced yield loss is related to both the intensification of extreme cold stress and the contribution of related components to yield in the three regions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.